© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. Residuals
    9. 4-RES-SM
    11. 13173
    Prev
    Next
    INDEX
    Explanations

    descriptions of residential properties and their features

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ctigges/pythia-70m-deduped__res-sm_processed/4-res-sm
    Prompts (Dashboard)
    32,768 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    standard
    Context Size
    128
    Dataset
    EleutherAI/the_pile_deduplicated
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    412
    +0.17
    1.0%
    309
    +0.14
    0.8%
    335
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    412
    +0.17
    0.14
    309
    +0.14
    0.11
    145
    +0.10
    0.08
    Negative Logits
    «
    -2.51
    ĥ½
    -2.35
    į
    -2.23
    Ī
    -2.19
    ĻĤ
    -2.08
    ¦
    -2.08
    ↵
    -2.00
    ↵            ↵
    -2.00
    ↵
    -2.00
     ↵
    -2.00
    POSITIVE LOGITS
     buildings
    2.92
     town
    2.60
     downtown
    2.54
     apartment
    2.51
     houses
    2.49
     streets
    2.48
     residential
    2.45
     city
    2.43
     apartments
    2.43
     stadium
    2.40
    Activations Density 2.305%

    No Known Activations